Question Bank for Semester End Examination (SEE)

Year/Sem: III/I Program: B. Tech

Branch: CSE(AI&ML) Academic Year: 2024-25

K1-Remembering; K2-Understanding; K3-Applying; K4-Analyzing; K4-Evaluating; K6-Creating

Short Answer Questions

Each Question Carriers two Marks:

Bloom’s
Course
Q. No. Question Taxonomy Marks Unit No.
Outcome
Level
Define a well-posed learning problem 2
1. CO1 K1 Unit-I
with an example. Marks
State the concept of inductive bias in 2
2. CO1 K1 Unit-I
machine learning. Marks
Explain the Find-S algorithm with a 2
3. CO1 K1 Unit-I
simple example. Marks
Find the maximally specific hypothesis
2
4. using the Find-S algorithm for a given CO1 K1 Unit-I
Marks
set of training data.
Define the version space in concept 2
5. CO1 K1 Unit-I
learning. Marks
Define a neural network. 2
6. CO2 K1 Unit-II
Marks
State the role of perceptrons in neural 2
7. CO2 K1 Unit-II
networks. Marks
Explain the significance of the back-
2
8. propagation algorithm in training neural CO2 K1 Unit-II
Marks
networks.
Identify appropriate problems for neural 2
9. CO2 K1 Unit-II
network learning. Marks
Define the concept of hypothesis 2
10. CO2 K1 Unit-II
evaluation in machine learning. Marks
11. CO3 K1 2 Unit-III
Define Bayesian learning.
Marks
12. State Bayes’ theorem and its application CO3 K1 2 Unit-III
in machine learning. Marks
13. Explain the concept of maximum CO3 K1 2 Unit-III
likelihood hypothesis. Marks
 Mid -II
14. Identify the role of the Naïve Bayes CO3 K1 2 Unit-III
classifier in text classification tasks. Marks
15. Define the EM algorithm and its CO3 K1 2 Unit-III
significance in machine learning. Marks
16. Define genetic algorithms and their CO4 K1 2 Unit-IV
application in machine learning. Marks
17. State the key principles behind CO4 K1 2 Unit-IV
reinforcement learning. Marks
18. Explain the process of hypothesis space CO4 K1 2 Unit-IV
search in genetic algorithms. Marks
19. Identify the role of Q-learning in CO4 K1 2 Unit-IV
reinforcement learning tasks. Marks
20. Define the concept of non-deterministic CO4 K1 2 Unit-IV
rewards and actions in reinforcement Marks
learning.
21. Define analytical learning and its role in CO5 K1 2 Unit-V
machine learning. Marks
22. State the significance of using prior CO5 K1 2 Unit-V
knowledge in analytical learning. Marks
23. Explain the PROLOG-EBG approach in CO5 K1 2 Unit-V
explanation-based learning. Marks
24. Identify the challenges in combining CO5 K1 2 Unit-V
inductive and analytical learning Marks
methods.
25. Define the concept of explanation-based CO5 K1 2 Unit-V
generalization (EBG) in machine Marks
learning.

Long Answer Questions

Bloom’s
Course
Q. No. Question Taxonomy Marks Unit -No
Outcome
Level
State and explain the general-to-specific
1. ordering in concept learning with CO2 K5 10 Marks Unit-I
examples.
Using the Candidate Elimination
2. algorithm, find the version space for a CO2 K4 10 Marks Unit-I
given set of hypotheses.
Derive an expression for the inductive
3. bias and explain its significance in CO2 K4 10 Marks Unit-I
decision tree learning.
Using an example, illustrate the process
4. of constructing a decision tree from CO2 K4 10 Marks Unit-I
training data.
5. Draw the decision tree for a given CO2 K5 10 Marks Unit-I
dataset and discuss the issues related to
 decision tree learning..
Explain the architecture of a multilayer
6. neural network and the process of back- CO3 K5 10 Marks Unit-II
propagation.
Derive the equations used in the back-
7. propagation algorithm for updating the CO3 K4 10 Marks Unit-II
weights in a neural network.
Analyze the challenges faced by neural
8. networks in learning from complex CO3 K4 10 Marks Unit-II
datasets.
Compare and contrast the performance
9. of different neural network architectures CO3 K4 10 Marks Unit-II
in solving real-world problems.
Evaluate the effectiveness of hypothesis
10. evaluation techniques in improving the CO3 K5 10 Marks Unit-II
accuracy of machine learning models.
Explain the process of Bayesian
11. CO4 K5 10 Marks Unit-III
learning with the help of an example.
Derive the maximum likelihood
12. hypothesis for predicting probabilities CO4 K4 10 Marks Unit-III
in machine learning.
Analyze the role of Bayesian belief
13. networks in capturing uncertainty in CO4 K4 10 Marks Unit-III
machine learning models.
Mid - II
Compare the performance of the Naïve
14. Bayes classifier with other classification CO4 K4 10 Marks Unit-III
algorithms in text classification.
Evaluate the effectiveness of the EM
15. algorithm in handling missing data in CO4 K5 10 Marks Unit-III
machine learning.
Explain the working of genetic
16. CO3 K5 10 Marks Unit-IV
algorithms with an example.
Derive the fitness function used in a
17. genetic algorithm for solving CO4 K4 10 Marks Unit-IV
optimization problems.
Analyze the relationship between
18. genetic algorithms and evolutionary CO4 K4 10 Marks Unit-IV
learning models.
Compare the effectiveness of rule-based
19. learning with genetic algorithms in CO4 K4 10 Marks Unit-IV
complex problem-solving scenarios.
Evaluate the impact of reinforcement
20. learning in improving the performance CO4 K5 10 Marks Unit-IV
of intelligent agents.
Derive the equation for explanation-
21. based generalization in analytical CO5 K4 10 Marks Unit-V
learning.
Analyze the challenges and benefits of
22. combining inductive and analytical CO5 K4 10 Marks Unit-V
learning methods.
23. Compare the effectiveness of analytical CO5 K4 10 Marks Unit-V
learning and inductive learning in
 different machine learning tasks.
Evaluate the role of prior knowledge in
enhancing the performance of machine
24. CO5 K5 10 Marks Unit-V
learning models through analytical
learning.
Explain the process of analytical
25. CO5 K5 10 Marks Unit-V
learning with an example.